yuweiiizz commited on
Commit
c18d426
1 Parent(s): b1da0f0

End of training

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - nan
4
+ license: apache-2.0
5
+ library_name: peft
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - mozilla-foundation/common_voice_16_1
10
+ base_model: openai/whisper-small
11
+ model-index:
12
+ - name: Whisper Small Taiwanese - LoRA
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Whisper Small Taiwanese - LoRA
20
+
21
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.9806
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.001
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 50
49
+ - num_epochs: 1
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 1.1346 | 0.2 | 100 | 1.2898 |
57
+ | 1.1269 | 0.4 | 200 | 1.1432 |
58
+ | 1.0896 | 0.6 | 300 | 1.0504 |
59
+ | 1.0369 | 0.8 | 400 | 1.0032 |
60
+ | 1.0069 | 1.0 | 500 | 0.9806 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.9.0
66
+ - Transformers 4.38.2
67
+ - Pytorch 2.1.2
68
+ - Datasets 2.18.0
69
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "WhisperForConditionalGeneration",
5
+ "parent_library": "transformers.models.whisper.modeling_whisper"
6
+ },
7
+ "base_model_name_or_path": "openai/whisper-small",
8
+ "beta1": 0.85,
9
+ "beta2": 0.85,
10
+ "bias": "none",
11
+ "deltaT": 10,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "init_r": 12,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_dropout": 0.1,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "orth_reg_weight": 0.5,
25
+ "peft_type": "ADALORA",
26
+ "r": 8,
27
+ "rank_pattern": null,
28
+ "revision": null,
29
+ "target_modules": [
30
+ "k_proj",
31
+ "q_proj",
32
+ "v_proj",
33
+ "out_proj",
34
+ "fc1",
35
+ "fc2"
36
+ ],
37
+ "target_r": 4,
38
+ "task_type": null,
39
+ "tfinal": 1000,
40
+ "tinit": 200,
41
+ "total_step": null,
42
+ "use_dora": false,
43
+ "use_rslora": false
44
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8a8a94116451d975c87e4a96ded30c06e48d1cb42bbf7d4d70690767c02a92
3
+ size 19548472
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
runs/Mar11_16-44-45_5e9ca3990ccb/events.out.tfevents.1710175506.5e9ca3990ccb.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2f75c9a17fcd5456d606fd84f514b4143c9deaf09c292ad96467820c64e05f
3
+ size 5918
runs/Mar11_16-57-18_5e9ca3990ccb/events.out.tfevents.1710176248.5e9ca3990ccb.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca2e8438b6d6ce07a73209b8285d463fc94569260293cc2ebfbc3ba8d6d64b1
3
+ size 6123
runs/Mar11_17-07-11_5e9ca3990ccb/events.out.tfevents.1710176843.5e9ca3990ccb.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:918aff35a9212fdaf422564f3453e27505b4ef0d39bcec78016e3ae8439de04f
3
+ size 8670
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8911085759a6ef429d68d6474119c492dd97d2cb0a24284e20c55af7a74395e6
3
+ size 5112